mlsanityData to 7 Oct 2026

UserLibri: A Dataset for ASR Personalization Using Only Text

arXiv 2207.00706 ↗First posted 2 Jul 2022eess.AS cs.CL cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Personalization of speech models on mobile devices (on-device personalization) is an active area of research, but more often than not, mobile devices have more text-only data than paired audio-text data. We explore training a personalized language model on text-only data, used during inference to improve speech recognition performance for that user. We experiment on a user-clustered LibriSpeech corpus, supplemented with personalized text-only data for each user from Project Gutenberg. We release this User-Specific LibriSpeech (UserLibri) dataset to aid future personalization research. LibriSpeech audio-transcript pairs are grouped into 55 users from the test-clean dataset and 52 users from test-other. We are able to lower the average word error rate per user across both sets in streaming and nonstreaming models, including an improvement of 2.5 for the harder set of test-other users when streaming.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 15 of its 28 references that are in the map. First posted on arXiv 2 Jul 2022.

Builds on

15 of 28 references.

References · 15

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  3. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  4. 2018Group Normalizationcited by 1,514
  5. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  6. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  7. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  8. 2017An analysis of incorporating an external language model into a sequence-to-sequence modelcited by 109
  9. 2020Hybrid Autoregressive Transducer (hat)cited by 106
  10. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 100
  11. 2020A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latencycited by 99
  12. 2019Speech Recognition with Augmented Synthesized Speechcited by 60
3 more
  1. 2019Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entitiescited by 41
  2. 2021Language model fusion for streaming end to end speech recognitioncited by 7
  3. 2021On-Device Personalization of Automatic Speech Recognition Models for Disordered Speechcited by 5

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 2.

6 papers.

  1. 2023Modeling Spoken Information Queries for Virtual Assistants: Open Problems, Challenges and Opportunitiescited by 4
  2. 2023SpellMapper: A non-autoregressive neural spellchecker for ASR customization with candidate retrieval based on n-gram mappingscited by 4
  3. 2024Toward Practical Automatic Speech Recognition and Post-Processing: a Call for Explainable Error Benchmark Guidelinecited by 4
  4. 2022Evaluation of Automated Speech Recognition Systems for Conversational Speech: A Linguistic Perspectivecited by 0
  5. 2023Wiki-En-ASR-Adapt: Large-scale synthetic dataset for English ASR Customizationcited by 0
  6. 2024Sequence-to-sequence models in peer-to-peer learning: A practical applicationcited by 0